Update README.md

README.md

@@ -69,7 +69,8 @@ print(outputs[0]["generated_text"][-1])
 
 ## Benchmark
 These benchmark are current benchmark and not final benchmark, due to recursive fine tuning techniques self improves over time:
-hf (pretrained=EpistemeAI/metatune-gpt20b-R0,parallelize=True,dtype=bfloat16), gen_kwargs: (temperature=1,top_p=1,max_new_tokens=1000), limit: 30.0, num_fewshot: 5, batch_size: 1
+
+- hf (pretrained=EpistemeAI/metatune-gpt20b-R0,parallelize=True,dtype=bfloat16), gen_kwargs: (temperature=1,top_p=1,max_new_tokens=1000), limit: 30.0, num_fewshot: 5, batch_size: 1
 |             Tasks             |Version|     Filter     |n-shot|  Metric   |   |Value |
 |-------------------------------|------:|----------------|-----:|-----------|---|-----:|
 |gsm8k_cot                      |      3|flexible-extract|     5|exact_match|↑  |0.91  |